| Challenge: | Recent automated ICD coding efforts improve performance by encoding medical notes and codes with additional data and knowledge bases. |
| Approach: | They propose a two-stage decoding mechanism to predict ICD codes using hierarchical properties of the codes to split the prediction into two steps: at first, predict the parent code and then predict the child code based on the previous prediction. |
| Outcome: | Experiments on the public MIMIC-III data show that the proposed model performs well in single-model settings without external data or knowledge. |
Similar Papers
Modeling Diagnostic Label Correlation for Automatic ICD Coding (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing work built a binary prediction for each label independently, ignoring the dependencies between labels. |
| Approach: | They propose a framework to capture the label correlation and train a reranking estimator to rescore the probability of each label set candidate generated by a base predictor. |
| Outcome: | The proposed framework improves on the best-performing predictors on MIMIC datasets. |
Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for ICD indexing have a heavy label distribution and a manual process . Xie and Xing (2017) propose a new approach to ICD re-ranking . |
| Approach: | They propose a "retrieve and re-rank" framework to allocate subsets of ICD codes to medical records . they leverage auxiliary knowledge of the electronic health records (EHR) and a discrete retrieval method . |
| Outcome: | The proposed method achieves state-of-the-art performance on the MIMIC-III benchmark. |
Automatic ICD Coding Exploiting Discourse Structure and Reconciled Code Embeddings (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies did not exploit the discourse structure of clinical notes, which provides rich contextual information for code assignment. |
| Approach: | They propose to leverage section type classification and section type embeddings to exploit the discourse structure of clinical notes to generate rich contextual information for code assignment. |
| Outcome: | The proposed model outperforms state-of-the-art models on a MIMIC dataset by a large margin. |
Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing approaches to assigning ICD codes to clinical text are time-consuming, labor intensive, and error-prone. |
| Approach: | They propose to adapt a Transformer-based model to a longformer model and use it to encode clinical narratives. |
| Outcome: | The proposed approach outperforms current state-of-the-art models in ICD coding with the label embeddings contributing to the good performance. |
A Neural Architecture for Automated ICD Coding (P18-1)
Copied to clipboard
| Challenge: | Medical coding is time-consuming, expensive, and error prone. |
| Approach: | They propose to use diagnosis descriptions (DDs) of a patient as inputs to select the most relevant ICD codes. |
| Outcome: | The proposed algorithms perform on a clinical dataset with 59K patient visits. |
Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for ICD indexing use machine learning to assign subset of codes to medical records . experimental results show proposed method achieves state-of-the-art performance on a number of measures. |
| Approach: | They propose a method that uses a deep dilated residual convolution encoder to learn document representations across different lengths of the texts. |
| Outcome: | The proposed method achieves state-of-the-art performance on a number of measures. |
Less is More: Explainable and Efficient ICD Code Prediction with Clinical Entities (2025.acl-long)
Copied to clipboard
| Challenge: | Clinical coding is labor-intensive and prone to delays, leading to global backlogs. |
| Approach: | They propose an approach that combines Named Entity Recognition (NER) and Assertion Classification (AC) to filter for clinically important content before supervised code prediction. |
| Outcome: | The proposed approach reduces training time by over half on a standard evaluation dataset compared to current methods . it uses Named Entity Recognition (NER) and Assertion Classification (AC) to filter for clinically important content before supervised code prediction. |
MedCodER: A Generative AI Assistant for Medical Coding (2025.naacl-industry)
Copied to clipboard
Krishanu Das Baksi, Elijah Soba, John J Higgins, Ravi Saini, Jaden Wood, Jane Cook, Jack I Scott, Nirmala Pudota, Tim Weninger, Edward Bowen, Sanmitra Bhattacharya
| Challenge: | Medical coding is time-consuming and error-prone due to large label space, lengthy text inputs, and the absence of supporting evidence annotations. |
| Approach: | They propose a Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. |
| Outcome: | The proposed framework outperforms existing methods on the International Classification of Diseases (ICD) code prediction scale. |
Fusion: Towards Automated ICD Coding via Feature Compression (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to assign ICD codes from unstructured clinical notes are noisy and prone to errors. |
| Approach: | They propose a feature compressed ICD coding model called Fusion to address this problem. |
| Outcome: | The proposed model outperforms existing models on two widely used datasets. |
AnEMIC: A Framework for Benchmarking ICD Coding Models (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Diagnostic coding is the task of assigning diagnosis codes defined by the ICD (International Classification of Diseases) standard to patient visits based on clinical notes. |
| Approach: | They propose to use an ICD coding framework to train and benchmark models . they correct errors in preprocessing and provide an interactive demo to analyze the models based on custom inputs. |
| Outcome: | The framework corrects errors in preprocessing and provides key models and weights trained on correctly preprocessed datasets. |